本文操作环境:windows7系统、php7.1版、dell g3电脑
php采集文章图片不显示怎么办?
php curl采集百度搜寻结果图片不显示问题的解决方法
1.根据关键字采集百度搜寻结果
根据关键字采集百度搜寻结果,可以使用curl实现,代码如下:
<?php
function docurl($url, $data=array(), $header=array(), $timeout=30){
$ch = curl_init();
curl_setopt($ch, curlopt_url, $url);
curl_setopt($ch, curlopt_httpheader, $header);
curl_setopt($ch, curlopt_returntransfer, true);
curl_setopt($ch, curlopt_followlocation, true);
curl_setopt($ch, curlopt_timeout, $timeout);
$response = curl_exec($ch);
if($error=curl_error($ch)){
die($error);
}
curl_close($ch);
return $response;
}
$wd = '仙剑奇侠传';
$url = 'http://www.baidu.com/s?wd='.urlencode($wd);
$data = array();
$header = array();
$response = docurl($url, $data, $header, 5);
echo $response;
?>
输出后发现有部分图片不能显示
2.采集后的图片不显示原因分析
直接在百度中搜寻,页面是可以显示图片的。使用firebug查看图片路径,发现采集的图片域名与在百度搜寻的图片域名不同。
采集返回的图片域名 t11.baidu.com
正常搜寻的图片域名 ss1.baidu.com
查看采集与正常搜寻的html,发现有个域名转换的js是不一样的
采集
var list = {
graph.baidu.com: http://graph.baidu.com,
t1.baidu.com:http://t1.baidu.com,
t2.baidu.com:http://t2.baidu.com,
t3.baidu.com:http://t3.baidu.com,
t10.baidu.com:http://t10.baidu.com,
t11.baidu.com:http://t11.baidu.com,
t12.baidu.com:http://t12.baidu.com,
i7.baidu.com:http://i7.baidu.com,
i8.baidu.com:http://i8.baidu.com,
i9.baidu.com:http://i9.baidu.com,
};
正常搜寻
var list = {
graph.baidu.com: https://sp0.baidu.com/-ayhfd0a2gu2pmbgoy3k,
t1.baidu.com:https://ss0.baidu.com/6on1bjeh1bf3odcf,
t2.baidu.com:https://ss1.baidu.com/6oz1bjeh1bf3odcf,
t3.baidu.com:https://ss2.baidu.com/6ov1bjeh1bf3odcf,
t10.baidu.com:https://ss0.baidu.com/6onwsjip0qiz8tyhnq,
t11.baidu.com:https://ss1.baidu.com/6onxsjip0qiz8tyhnq,
t12.baidu.com:https://ss2.baidu.com/6onysjip0qiz8tyhnq,
i7.baidu.com:https://ss0.baidu.com/73f1bjeh1bf3odcf,
i8.baidu.com:https://ss0.baidu.com/73x1bjeh1bf3odcf,
i9.baidu.com:https://ss0.baidu.com/73t1bjeh1bf3odcf,
};
因此可以断定是,百度根据来源地址、ip、header等参数,判断如果是采集的,则返回不同的js。
3.采集后图片不显示的解决方法
把采集到的html,根据定义的域名做一次批量转换即可。
<?php
function docurl($url, $data=array(), $header=array(), $timeout=30){
$ch = curl_init();
curl_setopt($ch, curlopt_url, $url);
curl_setopt($ch, curlopt_httpheader, $header);
curl_setopt($ch, curlopt_returntransfer, true);
curl_setopt($ch, curlopt_followlocation, true);
curl_setopt($ch, curlopt_timeout, $timeout);
$response = curl_exec($ch);
if($error=curl_error($ch)){
die($error);
}
curl_close($ch);
return $response;
}
// 域名转换
function cdomain($str){
$baidu_domain = '{
"http://graph.baidu.com": "https://sp0.baidu.com/-ayhfd0a2gu2pmbgoy3k",
"http://p.qiao.baidu.com":"https://sp0.baidu.com/5poxdtebkgqfm2e88ium_a",
"http://vse.baidu.com":"https://sp3.baidu.com/6qudsjip0qiz8tyhnq",
"http://hdpreload.baidu.com":"https://sp3.baidu.com/7lawfjuc_wui8t7jm9ickt-xh_",
"http://lcr.open.baidu.com":"https://sp2.baidu.com/8luysjw91qh3otqbppnn2djv",
"http://kankan.baidu.com":"https://sp3.baidu.com/7bm1dzeakgqfm2e88ium_a",
"http://xapp.baidu.com":"https://sp2.baidu.com/ylmwfhsm2q5ilbglnyg",
"http://dr.dh.baidu.com":"https://sp0.baidu.com/-kz1ad0a2gu2pmbgoy3k",
"http://xiaodu.baidu.com":"https://sp0.baidu.com/ylshczq6kgqfm2e88ium_a",
"http://sensearch.baidu.com":"https://sp1.baidu.com/5b11fzupbgm18t7jm9ickt-xh_",
"http://s1.bdstatic.com":"https://ss1.bdstatic.com/5en1bjq8aauym2zgoy3k",
"http://olime.baidu.com":"https://sp0.baidu.com/8bg4ctva2gu2pmbgoy3k",
"http://app.baidu.com":"https://sp2.baidu.com/9_qwsjip0qiz8tyhnq",
"http://i.baidu.com":"https://sp0.baidu.com/74oibt3kamgdnd_",
"http://c.baidu.com":"https://sp0.baidu.com/9foibt3kamgdnd_",
"http://sclick.baidu.com":"https://sp0.baidu.com/5bu_dtmfkgqfm2e88ium_a",
"http://nsclick.baidu.com":"https://sp1.baidu.com/8qujcd3n0sgco2kml5_y_d3",
"http://sestat.baidu.com":"https://sp1.baidu.com/5b1zede5kgqfm2e88ium_a",
"http://eclick.baidu.com":"https://sp3.baidu.com/-0u_dtmfkgqfm2e88ium_a",
"http://api.map.baidu.com":"https://sp2.baidu.com/9_q4sjopb1gco2kml5_y_d3",
"http://ecma.bdimg.com":"https://ss1.bdstatic.com/-0u0bxsm1a5bphglnyg",
"http://ecmb.bdimg.com":"https://ss0.bdstatic.com/-0u0bnsm1a5bphglnyg",
"http://t1.baidu.com":"https://ss0.baidu.com/6on1bjeh1bf3odcf",
"http://t2.baidu.com":"https://ss1.baidu.com/6oz1bjeh1bf3odcf",
"http://t3.baidu.com":"https://ss2.baidu.com/6ov1bjeh1bf3odcf",
"http://t10.baidu.com":"https://ss0.baidu.com/6onwsjip0qiz8tyhnq",
"http://t11.baidu.com":"https://ss1.baidu.com/6onxsjip0qiz8tyhnq",
"http://t12.baidu.com":"https://ss2.baidu.com/6onysjip0qiz8tyhnq",
"http://i7.baidu.com":"https://ss0.baidu.com/73f1bjeh1bf3odcf",
"http://i8.baidu.com":"https://ss0.baidu.com/73x1bjeh1bf3odcf",
"http://i9.baidu.com":"https://ss0.baidu.com/73t1bjeh1bf3odcf",
"http://b1.bdstatic.com":"https://ss0.bdstatic.com/9un1bjq8aauym2zgoy3k",
"http://ss.bdimg.com":"https://ss1.bdstatic.com/5av1bjqh_q23odcf",
"http://opendata.baidu.com":"https://sp0.baidu.com/8aqdcjqpaav3otqbppnn2djv",
"http://api.open.baidu.com":"https://sp0.baidu.com/9_q4sjw91qh3otqbppnn2djv",
"http://tag.baidu.com":"https://sp1.baidu.com/6lmfsjip0qiz8tyhnq",
"http://f3.baidu.com":"https://sp2.baidu.com/-uv1bjeh1bf3odcf",
"http://s.share.baidu.com":"https://sp0.baidu.com/5fozdde71mgco2kml5_y_d3",
"http://bdimg.share.baidu.com":"https://ss1.baidu.com/9ra4ct8abw9fktbgoi7o1ygwehsv",
"http://1.su.bdimg.com":"https://ss0.bdstatic.com/k4ozexsm1a5bphglnyg",
"http://2.su.bdimg.com":"https://ss1.bdstatic.com/kvozexsm1a5bphglnyg",
"http://3.su.bdimg.com":"https://ss2.bdstatic.com/kfozexsm1a5bphglnyg",
"http://4.su.bdimg.com":"https://ss3.bdstatic.com/lpozexsm1a5bphglnyg",
"http://5.su.bdimg.com":"https://ss0.bdstatic.com/l4ozexsm1a5bphglnyg",
"http://6.su.bdimg.com":"https://ss1.bdstatic.com/lvozexsm1a5bphglnyg",
"http://7.su.bdimg.com":"https://ss2.bdstatic.com/lfozexsm1a5bphglnyg",
"http://8.su.bdimg.com":"https://ss3.bdstatic.com/ipozexsm1a5bphglnyg"
}';
$domain = json_decode($baidu_domain, true);
foreach($domain as $k=>$v){
$str = str_replace($k, $v, $str);
}
return $str;
}
$wd = '仙剑奇侠传';
$url = 'http://www.baidu.com/s?wd='.urlencode($wd);
$data = array();
$header = array();
$response = docurl($url, $data, $header, 5);
echo cdomain($response); // 调用域名转换
?>
增加域名转换后,所有的图片都可以正常显示。
推荐学习:《php视频教程》
以上就是php采集文章图片不显示怎么办的详细内容。
